The test runner just went model-free on replay. tester-army's e2e, which led github trending on oct…
the test runner just went model-free on replay. tester-army's e2e, which led github trending on oct 6 with 1,398 new stars, has an agent drive your app tests once and then replays them without a single model call.
the regression suite now costs zero tokens per run.
Context
AICoder (Oct 5, 2026) reports that TesterArmy's open-source e2e tops GitHub daily trending, with natural-language agent steps for web and mobile tests that are replayed with zero model calls. TesterArmy's docs describe e2e as a TypeScript test runner where you choose how agentic each test is, from fully deterministic to fully agent-driven.
The docs say each agent step is an agent.act, agent.assert, agent.waitFor or agent.extract call, with a deadline and a model-call budget.
The zero model call replay and the GitHub trending lead match AICoder, which dates it Oct 5, not Oct 6. The 1,398 new stars was not seen in the sources read, so unsupported here, not refuted. The live GitHub trending page read shows 1,720 stars today for the repository, a different day's figure. 'The regression suite now costs zero tokens per run' is the author's opinion, and the docs say only agent steps use model calls.
Related work
- Trendshift: tester-army/e2e ↗Stars and trending history.
- GitHub trending ↗Live trending page.
- TesterArmy docs: debugging a run ↗Recordings and failure recaps.
Watch next
- Check the star history for Oct 6, 2026 on Trendshift.
Sources
- AICoder: TesterArmy's open-source e2e tops GitHub daily trendingaicoder.com
- TesterArmy: e2etester.army
- TesterArmy docs: how agent steps worke2e.tester.army
Provenance
The note above is reproduced unedited from the original post, first published on Threads on 11 October 2026 at 22:17 IST. Sources are the papers and datasets the note draws on.
View the original post ↗Embed this note
More notes
The air is now being asked to keep its own ledger
the air is now being asked to keep its own ledger: ecmwf’s aifs compo becomes the first ai model to forecast atmospheric composition globally every three hours, cleanair simulates 365 days of pm2.5 over china in ten seconds, and a unified framework maps six pollutants at one kilometer across the whole country. the air now files its own composition report.
read the note →The current is now being asked to draw its own map
the current is now being asked to draw its own map: china’s langya 2.0 predicts six ocean phenomena including internal waves and mesoscale eddies, a deep net called wenhai resolves eddies globally with air sea flux formulas built in, and scripps infers surface currents from the way temperature patterns deform in satellite images. the ocean now files its own circulation report.
read the note →The soil is now being asked to report its own carbon
the soil is now being asked to report its own carbon: a nix color sensor paired with generative data augmentation predicts soil organic carbon without a lab, random forest drives 74 percent of soil health mapping studies, and sentinel 2 tracks five year carbon change across france and italy from 922 samples. the dirt now files its own carbon account.
read the note →